How vulnerable is my policy? Adversarial attacks on modern behavior cloning policies
Learning from Demonstration (LfD) algorithms have shown promising results in robotic manipulation tasks, but their vulnerability to adversarial attacks remains underexplored. This paper presents a comprehensive study of adversarial attacks on both classic and recently proposed algorithms, including Behavior Cloning (BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and VQ-Behavior Transformer (VQ-BET). We study the vulnerability of these methods to untargeted, targeted and universal adversarial perturbations. While explicit policies, such as BC, LSTM-GMM and VQ-BET can be attacked in the same manner as standard computer vision models, we find that attacks for implicit and denoising policy models are nuanced and require developing novel attack methods. Our experiments on several simulated robotic manipulation tasks reveal that most of the current methods are highly vulnerable to adversarial perturbations. We also show that these attacks are transferable across algorithms, architectures, and tasks, raising concerning security vulnerabilities with potentially a white-box threat model. In addition, we test the efficacy of a randomized smoothing, a widely used adversarial defense technique, and highlight its limitation in defending against attacks on complex and multi-modal action distribution common in complex control tasks. In summary, our findings highlight the vulnerabilities of modern BC algorithms, paving way for future work in addressing such limitations.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseDenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)
Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from observed behavior. In this paper, we propose…
Deep Reinforcement LearningImitation Learningreinforcement-learningReinforcement Learning (RL)Physical Adversarial Attacks for Surveillance: A Survey
Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks - maliciously crafted input…
Action RecognitionSurveyComparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks
Nowadays, neural-network-based image- and video-quality metrics perform better than traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving vi…
Adversarial RobustnessVulnerability of Deep Reinforcement Learning to Policy Induction Attacks
Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on De…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically lim…